housing_analysis

#Import libraries
library(ggplot2)
library(wordcloud)

## Loading required package: RColorBrewer

library(RColorBrewer)
library(wordcloud2)
library(reshape)
library(tm)

## Loading required package: NLP

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

library(stringr)
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:reshape':
## 
##     rename

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

#Reads in housing data
housing <- read.csv('housing_cleaned.csv')

#Creates list of columns in df
housing_columns = colnames(housing)

#Drops 'X' column from df
housing_columns = housing_columns[-1]
housing_columns = housing_columns[-11]
housing = subset(housing, select = housing_columns)

#Sub-Categories
#Number/types of sub-categories-bar chart

#Creates a bar graph of sub-category types
sub_cat_counts <- function(state) {
  if(state=="All Sample States") {
    sub_cats <- ggplot(housing, aes(x=Sub.categories)) + geom_bar(fill="blue") + labs(x="Sub-Category", y="Counts", title="Types of Sub-Categories") + theme(axis.text.x = element_text(angle = 25))
    ggplotly(sub_cats)
  }
  else { #fix
    State <- str_to_title(state)
    state_input <- housing[housing[, "State"]==state, ]
    state_df <- data.frame()
    state_df <- rbind(state_df, state_input)
    sub_cats <- ggplot(state_df, aes(x=Sub.categories)) + geom_bar(fill="blue") + labs(x="Sub-Category", y="Counts", title="Types of Sub-Categories") + theme(axis.text.x = element_text(angle = 25))
    ggplotly(sub_cats)
  }
}

sub_cat_counts("All Sample States")

#Tool
#Number/types of tools-pie chart

#fix
tool_barchart <- function(state) {
  if(state=="All Sample States") {
    tools <- ggplot(housing, aes(x=Tool)) + geom_bar(fill="blue") + labs(x="Tool", y="Count", title="Types of Tools") + theme(axis.text.x = element_text(angle = 45))
  ggplotly(tools)
  }
  else {
    State <- str_to_title(state)
    state_input <- housing[housing[, "State"]==state, ]
    state_df <- data.frame()
    state_df <- rbind(state_df, state_input)
    tools <- ggplot(state_df, aes(x=Tool)) + geom_bar(fill="blue") + labs(x="Tool", y="Count", title="Types of Tools") + theme(axis.text.x = element_text(angle = 45))
  ggplotly(tools)
  }
}

tool_barchart("California")

#Tool Name


#Word cloud for tool names
#Input is designated state
tool_cloud <- function(state) {
  if(state=="all states"){
    combo <- ""
    for (i in 1:nrow(housing)) {
      combo <- paste(combo, housing$Tool.Name[i], sep="")
    }
  }
  else{
  #Combines all variables into one string
    combo <- ""
    for (i in 1:nrow(housing)) {
      if(housing$State[i]==state) {
        combo <- paste(combo, housing$Tool.Name[i], sep="")
      }
    }
  }

  #Turns string into corpus of words
  docs <- Corpus(VectorSource(combo))

  #Cleaning of corpus
  docs <- docs %>% tm_map(removeNumbers) %>% tm_map(removePunctuation) %>% tm_map(stripWhitespace)
  docs <- tm_map(docs, content_transformer(tolower))
  docs <- tm_map(docs, removeWords, stopwords("english"))

  #Turns corpus into term-document-matrix
  dtm <- TermDocumentMatrix(docs)
  mtx <- as.matrix(dtm)
  words <- sort(rowSums(mtx), decreasing = TRUE)
  df <- data.frame(word = names(words), freq=words)

  #Creates wordcloud
  set.seed(33)

  cloud <- wordcloud(words = df$word, freq = df$freq, min.freq = 1, max.words = 100, random.order = FALSE, rot.per = 0, colors = brewer.pal(4, "Set1"))
  
  return(cloud)
}

#Variables

#Word cloud for variable names
#Input is designated state
variable_cloud <- function(state) {
  if(state=="all states"){
    combo <- ""
    for (i in 1:nrow(housing)) {
      combo <- paste(combo, housing$Variables[i], sep="")
    }
  }
  else{
  #Combines all variables into one string
    combo <- ""
    for (i in 1:nrow(housing)) {
      if(housing$State[i]==state) {
        combo <- paste(combo, housing$Variables[i], sep="")
      }
    }
  }

  #Turns string into corpus of words
  docs <- Corpus(VectorSource(combo))

  #Cleaning of corpus
  docs <- docs %>% tm_map(removeNumbers) %>% tm_map(removePunctuation) %>% tm_map(stripWhitespace)
  docs <- tm_map(docs, content_transformer(tolower))
  docs <- tm_map(docs, removeWords, stopwords("english"))

  #Turns corpus into term-document-matrix
  dtm <- TermDocumentMatrix(docs)
  mtx <- as.matrix(dtm)
  words <- sort(rowSums(mtx), decreasing = TRUE)
  df <- data.frame(word = names(words), freq=words)

  #Creates wordcloud
  set.seed(33)

  cloud <- wordcloud(words = df$word, freq = df$freq, min.freq = 1, max.words = 100, random.order = FALSE, rot.per = 0, colors = brewer.pal(4, "Set1"))
  
  return(cloud)
}

#Geographic Levels
#Number/types of geographic levels-pie chart

#fix
geo <- ggplot(housing, aes(x=Geographic.Levels)) + geom_bar(fill="blue") + labs(x="Geographic Levels", y="Count", title="Types of Geoographic Levels") + theme(axis.text.x = element_text(angle = 45))
ggplotly(geo)

#Data Sources-Census
#Number/types of census sources-bar chart, pie chart, count

#fix: exclude if value is NA
#fix: by state
census <- ggplot(housing, aes(x=Data.Sources.Census)) + geom_bar(fill="blue") + labs(x="Census Source", y="Count", title="Types of Census Sources") + theme(axis.text.x = element_text(angle = 45))
ggplotly(census)

#Data Sources-Non Census
#Number/types of non-census sources-bar chart, pie chart, count

#fix: exclude if value is NA
#fix: by state
non_census <- ggplot(housing, aes(x=Data.Sources.Non.Census)) + geom_bar(fill="blue") + labs(x="Data Sources", y="Count", title="Data Sources") + theme(axis.text.x = element_text(angle = 45))
ggplotly(non_census)

#Direct Links to Census
#Count

sum(!housing$Direct.links.to.Census=='n')

## [1] 166

#Age of Data
#Number/types of age of data-pie chart
#Oldest data, most recent

#Historical Data
#Count
sum(housing$Historical.data=='y')

## [1] 0